Texture- and Shape-based Adversarial Attacks for Overhead Image Vehicle Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912577216315392 |
|---|---|
| author | Yeghiazaryan, Mikael Namburu, Sai Abhishek Siddhartha Kim, Emily Panev, Stanislav de Melo, Celso De la Torre, Fernando Hodgins, Jessica K. |
| author_facet | Yeghiazaryan, Mikael Namburu, Sai Abhishek Siddhartha Kim, Emily Panev, Stanislav de Melo, Celso De la Torre, Fernando Hodgins, Jessica K. |
| contents | Detecting vehicles in aerial images is difficult due to complex backgrounds, small object sizes, shadows, and occlusions. Although recent deep learning advancements have improved object detection, these models remain susceptible to adversarial attacks (AAs), challenging their reliability. Traditional AA strategies often ignore practical implementation constraints. Our work proposes realistic and practical constraints on texture (lowering resolution, limiting modified areas, and color ranges) and analyzes the impact of shape modifications on attack performance. We conducted extensive experiments with three object detector architectures, demonstrating the performance-practicality trade-off: more practical modifications tend to be less effective, and vice versa. We release both code and data to support reproducibility at https://github.com/humansensinglab/texture-shape-adversarial-attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_16358 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Texture- and Shape-based Adversarial Attacks for Overhead Image Vehicle Detection Yeghiazaryan, Mikael Namburu, Sai Abhishek Siddhartha Kim, Emily Panev, Stanislav de Melo, Celso De la Torre, Fernando Hodgins, Jessica K. Computer Vision and Pattern Recognition Detecting vehicles in aerial images is difficult due to complex backgrounds, small object sizes, shadows, and occlusions. Although recent deep learning advancements have improved object detection, these models remain susceptible to adversarial attacks (AAs), challenging their reliability. Traditional AA strategies often ignore practical implementation constraints. Our work proposes realistic and practical constraints on texture (lowering resolution, limiting modified areas, and color ranges) and analyzes the impact of shape modifications on attack performance. We conducted extensive experiments with three object detector architectures, demonstrating the performance-practicality trade-off: more practical modifications tend to be less effective, and vice versa. We release both code and data to support reproducibility at https://github.com/humansensinglab/texture-shape-adversarial-attacks. |
| title | Texture- and Shape-based Adversarial Attacks for Overhead Image Vehicle Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.16358 |